A modular neural network decision support system in EMG diagnosis
ΣυγγραφέαςChristodoulou, Christodoulos I.
Pattichis, Constantinos S.
Fincham, W. F.
SourceJournal of Intelligent Systems
Google Scholar check
MetadataΕμφάνιση πλήρους εγγραφής
Motor unit action potentials (MUAPs) recorded during routine electromyographic (EMG) examination provide important information for the assessment of neuromuscular disorders. The objective of this study was to design, develop, and test a decision support system which mimics the decision making process carried out by the expert neurophysiologist in MUAP analysis where: (i) the statistics of MUAP features are compared to normal reference values, and (ii) the individual MUAP waveforms are visually evaluated in sequence. The system consisted of the following two modular neural network subsystems, hi the first subsystem, the statistics for each subject of multiple features extracted from the MUAP waveforms were fed into multiple classifiers, and the classification results were combined in order to improve the diagnostic yield. The feature sets computed, were: (i) the time domain parameters, (ii) the frequency domain parameters, (iii) the autoregressive coefficients, (iv) the cepstral coefficients and (v) the wavelet transform coefficients. The classifiers implemented were: (i) the back-propagation (BP), (ii) the radial basis function (RBF) network and (iii) the self-organising feature map (SOFM). In the second subsystem, the individual MUAPs obtained by a subject were fed sequentially into the classifier and the classification results were combined. For this subsystem the time domain parameters, the MUAP waveforms, and the SOFM classifier were used. The outputs of the two subsystems were further combined in order to obtain the overall diagnostic yield. The proposed system was developed for the assessment of normal subjects and subjects suffering with myopathy and motor neuron disease. It was shown that the modular neural networks system enhanced the diagnostic performance of the individual classifiers making the whole system more robust and reliable.